LOCAL POSITIONING APPARTUS, AND METHOD THEREFOR

• US 20020031242A1
• Filed: 12/21/1998
• Published: 03/14/2002
• Est. Priority Date: 08/28/1996
• Status: Active Grant

• Current Assignee: Atsushi Iisaka, Mamoru Kaneko, Nobuhiko Yasui
• Original Assignee: Atsushi Iisaka, Mamoru Kaneko, Nobuhiko Yasui
• Inventors: KANEKO, MAMORU, IISAKA, ATSUSHI, YASUI, NOBUHIKO
• Granted Patent: US 6,493,458 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: B60T 2201/08 Lane monitoring; Lane Keeping Systems
• CPC Class Codes: B60T 2201/089 using optical detection
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication

Abstract

An apparatus and method for correctly determining the position of a vehicle in a traffic lane by obtaining correct information about the position of the traffic lane without being affected by variations in the road surface, weather, time of day, or such imaging conditions as fixed or moving lighting, are provided. An edge signal or a high spatial frequency component and a luminance signal of a low spatial frequency component of a digital image signal representing the view of the local area to the front of a vehicle are extracted. A road contour signal is then extracted from the edge signal, and a road region signal is extracted from the luminance signal. The position of the lane Sre is then detected with high precision by evaluating the lane contour Sre based on the road region signal Srr and lane contour data Sre.

Claims

1. A local positioning apparatus for detecting a local position of a subject capable of advancing in a direction relating to a lane in a local area based on a digital image signal representing a local image of an area in an advancing direction of said subject, said apparatus comprising:

a first image signal generating means for extracting a high spatial frequency component from the digital image signal, and producing an edge signal;

a contour extraction means for extracting a contour of a lane based on the edge signal, and generating road contour data;

a second image signal generating means for extracting a low spatial frequency component from the digital image signal, and producing a luminance signal;

a lane area extraction means for extracting the lane area based on the luminance signal and generating road region data; and

a lane detection means for detecting the lane position based on the lane contour data and road region data, and producing a lane detection signal.

2. A local positioning apparatus according to claim 1, wherein said lane area extraction means comprises a lane region setting means for adding a particular tolerance range to said road region data to produce second road region data representing a lane candidate area in which a lane may be present;

and

said lane detection means compares said road contour data and second road region data to detect whether said second road region data or lane candidate area is larger.

3. A local positioning apparatus according to claim 2, wherein said lane detection means defines said road contour data as the lane detection signal when said second road region data is within said lane candidate area.

4. A local positioning apparatus according to claim 2, wherein said lane detection means causes said contour extraction means to extract a new contour when said second road region data is not within said lane candidate area.

5. A local positioning apparatus according to claim 1, further comprising an in-lane position detector for detecting said position of said subject in said lane based on said lane detection signal.

6. A local positioning apparatus according to claim 1, wherein said lane area extraction means extracts pixels in luminance signal in a particular luminance range to produce road region data.

7. A local positioning apparatus according to claim 6, wherein said lane area extraction means comprises a first pixel luminance extraction means for extracting a first luminance from a pixel representing a farthest point removed a first particular distance;

and

extracts pixels with luminance below said first luminance to generate road region data.

8. A local positioning apparatus according to claim 7, wherein said lane area extraction means further comprises a second pixel luminance extraction means for extracting a second luminance from a pixel representing a point closer than first particular distance;

and

extracts pixels with luminance between said first luminance and said second luminance to generate road region data.

9. A local positioning apparatus according to claim 7, wherein first particular distance is set according to the speed of travel of said subject.

10. A local positioning apparatus according to claim 7, wherein first pixel luminance extraction means extracts a first luminance from a pixel representing an image at a particular horizontal position on a horizontal line passing through a point removed a first particular distance.

11. A local positioning apparatus according to claim 10, wherein said particular horizontal position is determined ad hoc according to said steering angle of said subject.

18. A road area extraction apparatus according to claim 17, wherein said road area combining means combines segmented areas at said vehicle position in said lateral direction to said road width, and combines areas vertically such that said upper area has a width less than said width of said lower area.

12. A local positioning method for detecting a local position of a subject capable of advancing in a direction relating to a lane in a local area based on a digital image signal representing a local image of an area in an advancing direction of s aid subject, comprising:

a first image signal generating step for extracting a high spatial frequency component from said digital image signal, and producing an edge signal;

a contour extraction step for extracting a contour of a lane based on said edge signal, and generating road contour data;

a second image signal generating step for extracting a low spatial frequency component from said digital image signal, and producing a luminance signal;

a lane area extraction step for extracting said lane area based on said luminance signal and generating road region data; and

a lane detection step for detecting said lane position based on said lane contour data and road region data, and producing a lane detection signal.

13. A road area detection method for extracting a road area as a polygonal area in an image plane centered on a vehicle, comprising:

a road area extraction method for segmenting a road area using road image data; and

a road polygon detection method for a polygonal area including a point directly before a vehicle in an image plane from said areas separated by said road area extraction method.

14. A road area extraction apparatus comprising:

a road imaging device for capturing an image of a road before a vehicle;

a brightness histogram generating means for creating a brightness histogram using said road image data from said road imaging device;

a road brightness separating means for separating from a brightness histogram said area containing luminance values immediately before said vehicle and contained between valleys in said brightness histogram generated by said brightness histogram generating means; and

a road polygon detecting means for detecting a polygonal area including a point directly before a vehicle in an image plane in said areas separated by said road brightness separating means;

wherein said road area is extracted as a polygonal area in an image plane centered on a vehicle.

15. A road area extraction apparatus comprising:

a road imaging device for capturing an image of a road before a vehicle;

a brightness pattern detection means for detecting said surface brightness pattern immediately before said vehicle using said road image data from said road imaging device; and

a brightness pattern separation means for separating road areas with a brightness pattern similar to said road brightness pattern immediately before said vehicle supplied from said brightness pattern detection means, wherein a road area is separated from said image by measuring said brightness pattern of said road surface.

16. A road area extraction apparatus comprising:

a road imaging device for capturing an image of a road before a vehicle;

a brightness histogram generating means for creating a brightness histogram using said road image data from said road imaging device; and

a pixel count road area extraction means for setting on said brightness histogram a range of a predetermined pixel count constituting a road area using a brightness position directly before a vehicle using said brightness histogram generated by said brightness histogram generating means, wherein a brightness area is set in said brightness histogram using a brightness value immediately before said vehicle by first obtaining said pixel count of said road area to separate road areas in said image.

17. A road area extraction apparatus comprising:

a road imaging device for capturing an image of a road before a vehicle;

an image separating means for segmenting an image from road image data from said road imaging device based on image characteristics;

a road area combining means for combining a segmented area of said vehicle position in said image with areas adjacent thereto on both sides for said road width only using road width data from a road width detection means described below and segment data from said image separating means, and repeating this operation to a particular position toward said top of said image to extract a road area; and

a road width detection means for calculating said road width at various heights in said image from said extracted road areas from said road area combining means, wherein image segments are combined to extract said road area based on road width information detected from said previous image.

19. A road direction detection apparatus comprising:

a road imaging device for capturing an image of a road before a vehicle;

an image separating means for segmenting an image from road image data from said road imaging device based on image characteristics;

a road area combining means for combining a segmented area of said vehicle position in said image with areas adjacent thereto on both sides for said road width only using road width data from a road width detection means described below and segment data from said image separating means, and repeating this operation to a particular position toward said top of said image to extract a road area;

a road width detection means for calculating said road width at various heights in said image from said extracted road areas from said road area combining means;

a road area correlation detection means for calculating a correlation between a triangle defined by a vanishing point at a selected position on a particular vanishing line and two road edge data points at said image bottom determined by said road width detection means, and an extracted road area supplied by said road area combining means, and detecting said vanishing point yielding said greatest correlation value; and

a road direction detection means for detecting said direction of said road to said front of said vehicle from said vanishing point position yielding said greatest correlation value as detected by said road area correlation detection means, wherein the direction of said road relative to the vehicle is detected by obtaining said correlation between an extracted road area and a triangle defined by a vanishing point at a selected position on a particular vanishing line and two road edge data points.